Skip to content

materials.md

Latest commit

 

History

History
44 lines (37 loc) · 4.87 KB

materials.md

File metadata and controls

44 lines (37 loc) · 4.87 KB
layout page
title Materials
permalink /materials/

What to Read: Textbook(s)

Detailed instructor notes in addition to supplementary reading material from the following books.

  1. (Thrun) “Probabilistic Robotics” by Sebastian Thrun, Wolfram Burgard and Dieter Fox. PDF{:target="_blank"}
  2. (Barfoot) “State Estimation for Robotics” by Tim Barfoot. PDF{:target="_blank"}
  3. (Lavalle) “Planning Algorithms” by Steve Lavalle. PDF{:target="_blank"}
  4. (Sutton) “Reinforcement Learning: An Introduction” by Richard Sutton and Andrew Barto PDF{:target="_blank"}
  5. (d2l) Dive into Deep Learning by Aston Zhang, Zack Lipton, Mu Li and Alex Smola available at https://d2l.ai{:target="_blank"} is a good reference to read about deep learning.
  6. (Russell) “Artificial Intelligence: A Modern Approach” by Stuart Russell and Peter Norvig. PDF{:target="_blank"}
  7. (Rugh) “Linear System Theory” by Wilson J Rugh. PDF{:target="_blank"}

Additional Reading Material

The following books contain some advanced material. You can use it for your own reference and to brush up fundamentals of machine learning and optimization.

  1. “Pattern Recognition and Machine Learning” by Christopher Bishop. PDF{:target="_blank"}
  2. “An Invitation to 3-D Vision: From Images to Models“ by Yi Ma, Stefano Soatto, Jana Kosecka, Shankar Sastry. PDF{:target="_blank"}
  3. “Reinforcement Learning and Optimal Control” by Dmitri Bertsekas. Material{:target="_blank"}
  4. “Feedback Systems: An Introduction for Scientists and Engineers” by Karl Johan Astrom and Richard M. Murray, PDF{:target="_blank"}
  5. (Advanced) “Linear Systems Theory” by João P. Hespanha. Website{:target="_blank"}
  6. (Fairly advanced) “Stochastic Models, Information Theory, and Lie Groups, Volume 1: Classical Results and Geometric Methods” by Gregory Chirikjian. PDF{:target="_blank"}

Computational Resources

Almost all coursework can be done using your laptop. We will use PyTorch https://pytorch.org{:target="_blank"} and MuJoCo http://www.mujoco.org{:target="_blank"} in the later parts of the course for reinforcement learning. If you want additional computational resources, you can take a look at the following. Free: Google Colab https://colab.research.google.com{:target="_blank"} is a very good platform with a good GPU that you can use for most small-scale experiments. Gradient https://gradient.paperspace.com{:target="_blank"} is another free tool with more generous compute resources (6-hour timeouts and persistent sessions). If you haven’t used it already Google Cloud Project gives $300 of starter credits https://cloud.google.com/free{:target="_blank"}. Paid: You can also sign up for Google Colab Pro https://colab.research.google.com/signup{:target="_blank"} for a very reasonable $10/month to get access to faster GPUs and less restrictive preemption of jobs.

Use Latex !

  • We require you to use LaTeX for your reports in this course, as LaTeX is a skill you should learn if you haven’t already!
  • We will provide you with the templates to structure your submissions.
  • Additionally,
    • Official website of latex: http://www.latex-project.org/{:target="_blank"}
    • TEX editor for windows: WinEdt{:target="_blank"}, LEd{:target="_blank"}, TexMaker{:target="_blank"}
    • TEX editor for MacOS: TeXPad{:target="_blank"}, Latexian{:target="_blank"}
    • Online TEX editor: Overleaf{:target="_blank"}, LaTeX Base{:target="_blank"}
    • Please share the best TEX editor or integrated solutions in your mind to the class via Pizza.

Issac Asimov

A PDF copy of the book I-Robot (1950) - which contains the short story Liar (originally published in 1941), within which the term Robot was coined. PDF{:target="_blank"}